Machine learning applications in proteomics research: How the past can boost the future

Businesses and consumers increasingly use artificial intelligence (“AI”)— and specifically machine learning (“ML”) applications—in their daily work. ML is often used as a tool to help people perform their jobs more efficiently, but increasingly it is becoming a technology that may eventually replace humans in performing certain functions. An AI recently beat humans in a reading comprehension test, and there is an ongoing race to replace human drivers with self-driving cars and trucks. Tomorrow there is the potential for much more—as AI is even learning to build its own AI. As the use of AI technologies continues to expand, and especially as machines begin to act more autonomously with less human intervention, important questions arise about how we can best integrate this new technology into our society, particularly within our legal and compliance frameworks. The questions raised are different from those that we have already addressed with other technologies because AI is different. Most previous technologies functioned as a tool, operated by a person, and for legal purposes we could usually hold that person responsible for actions that resulted from using that tool. For example, an employee who used a computer to send a discriminatory or defamatory email could not have done so without the computer, but the employee would still be held responsible for creating the email. While AI can function as merely a tool, it can also be designed to act after making its own decisions, and in the future, will act even more autonomously. As AI becomes more autonomous, it will be more difficult to determine who—or what—is making decisions and taking actions, and determining the basis and responsibility for those actions. These are the challenges that must be overcome to ensure AI’s integration for legal and compliance purposes.

Download Full-text

PAAIcon2016: Multivariate statistics for hydrogeology: moving forward from "the present is the key to the past"

10.31227/osf.io/fbgmy ◽

2017 ◽

Author(s):

Dasapta Erwin Irawan

Keyword(s):

Machine Learning ◽

Principal Component Analysis ◽

Cluster Analysis ◽

Open Source ◽

Multivariate Statistics ◽

Family Life ◽

Principal Component ◽

Demographic Health Survey ◽

The Past ◽

The Future

This abstract has been presented at the PAAI conference 2016, 16-17 Nov 2016. Consists of to part: Part 1 Introduction to Open Science (zip file) and Part 2 Multivariate statistics in hydrogeology.ABSTRACT Geology is one of the oldest science in the world. Originated from natural science, it grows from the observation of sea shells to the sophisticated interpretation of the earth interior. On recent development geological approach need to be more quantitative, related to the needs prediction and simulation. Geology has shifted from “the present is the key to the past” towards “the present is the key to the past as the base of prediction of the future”. Hydrogeology is one of the promising branch of geology that relies more to quantitative analysis. Multivariate statistics is one of the most frequently used resources in this field. We did some literature search and web scraping to analyze current situation and future trend of multivariate statistics application for geological synthesis. We used several sets of keywords but this set gave the most satifying results: “(all in title) multivariate statistics (and) groundwater”, on Google Scholar, Crossref, and ScienceOpen database. The final result was 164 papers. We used VosViewer and Zotero to do some text mining operations. Based on the analysis we can draw some results. Cluster analysis and principal component analysis are still the most frequently used method in hydrogeology. Both are mostly used to extract hydrochemical and isotope data to analyze the hydrogeological nature of groundwater flow. More machine learning methods have been introduced in the last five years in hydrogeological science. `Random forest` and `decision tree` technique are used extensively to learn the from physical and chemical properties of groundwater. Open source tools have also shifted the use of major statistical or programming language such as: SAS and Matlab. Python and R programming are the two famous open source applications in this field. We also note the increase of papers to discuss hydrogeology and public health sector. Therefore such methods are also being used to analyze open demographic data like DHS (demographic health survey) and FLS (Family Life Survey). Strong community of programmer makes the exponential development of both languages, via platform like Github. This has become the future of hydrogeology. ABSTRAK Geologi adalah salah satu ilmu tertua di dunia. Berasal dari ilmu alam, ia berkembang dari observasi kerang laut ke arah interpretasi interior bumi yang kompleks. Dalam perkembangannya saat ini, geologi memerlukan pendekatan yang lebih kuantitatif, berkaitan dengan kebutuhan untuk prediksi dan simulasi. Geologi telah bergeser dari “the present is the key to the past” (saat ini adalah kunci menuju masa lalu) menjadi “the present is the key to the past as the base of prediction of the future” (saat ini adalah kunci menuju masa lalu dan sebagai dasar prediksi masa depan. Hidrogeologi adalah salah satu cabang ilmu geologi yang bersandar kepada analisis kuantitatif. Statistik multivariabel adalah salah satu metode yang digunakan dalam bidang ini. Kami telah melakukan telaah literatur dan penyadapan web untuk menganalisis kondisi saat ini dan trend masa depan tentang aplikasi statistik multivariabel untuk sintesis geologi. Beberapa set kata kunci digunakan, tetapi yang berikut ini memberikan hasil paling memuaskan: “(all in title) multivariate statistics (and) groundwater”. Database Google Scholar, Crossref, dan ScienceOpen menjadi sumber informasi yang menghasilkan hasil terseleksi sebanyak 164 makalah ilmiah. Kami menggunakan aplikasi VosViewer and Zotero untuk mengolah data teks (text mining). Berdasarkan analisis, cluster analysis dan principal component analysis masih menjadi teknik yang paling banyak dipakai. Keduanya umumnya digunakan untuk mengesktrak data hidrokimia dan isotop untuk menganalisis kondisi hidrogeologi dan aliran air tanah. Lebih banyak lagi metode machine learning (pembelajaran mesin) telah dikenalkan dan digunakan dalam lima tahun terakhir. Teknik “Random forest” and “decision tree” yang merupakan pengembangan dari teknik regresi linear juga telah banyak digunakan untuk mempelajari sifat fisik dan kimia air tanah. Penggunaan aplikasi open source juga telah menggeser piranti lunak berbayar yang mahal, seperti SAS and Matlab. Bahasa pemrograman Python and R adalah beberapa saja yang terkenal dalam bidang machine learning. Kami juga menangkap peningkatan jumlah makalah yang isinya merupakan irisan antara bidang hidrogeologi dan kesehatan masyarakat. Karena itu teknik machine learning juga digunakan untuk menganalisis data terbuka demografi seperti DHS (demographic health survey) dan FLS (Family Life Survey). Komunitas programmer yang kuat mampu mengembangan piranti lunak open source ini secara eksponensial, melalui platform seperti Github. Hal ini telah menjadi masa depan dari hidrogeologi.

Download Full-text

The Education of the Human Factors Engineer in the Age of Data Science

Proceedings of the Human Factors and Ergonomics Society Annual Meeting ◽

10.1177/1071181320641109 ◽

2020 ◽

Vol 64 (1) ◽

pp. 480-484

Author(s):

Daniel Hannon ◽

Esa Rantanen ◽

Ben Sawyer ◽

Ashley Hughes ◽

Katherine Darveau ◽

...

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Human Factors ◽

Data Science ◽

Panel Discussion ◽

Quantitative Skills ◽

The Future ◽

Relevant Role ◽

Machine Learning Applications

The continued advances in artificial intelligence and automation through machine learning applications, under the heading of data science, gives reason for pause within the educator community as we consider how to position future human factors engineers to contribute meaningfully in these projects. Do the lessons we learned and now teach regarding automation based on previous generations of technology still apply? What level of DS and ML expertise is needed for a human factors engineer to have a relevant role in the design of future automation? How do we integrate these topics into a field that often has not emphasized quantitative skills? This panel discussion brings together human factors engineers and educators at different stages of their careers to consider how curricula are being adapted to include data science and machine learning, and what the future of human factors education may look like in the coming years.

Download Full-text

Recent Development of Artificial Intelligence Applied in Echocardiography: A Review (Preprint)

10.2196/preprints.17227 ◽

2019 ◽

Author(s):

Lu Liu ◽

Ahmed Elazab ◽

Baiying Lei ◽

Tianfu Wang

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Deep Learning ◽

Cardiovascular Diseases ◽

Disease Diagnosis ◽

Machine Learning Techniques ◽

Tissue Segmentation ◽

The Past ◽

Learning Techniques ◽

The Future

BACKGROUND Echocardiography has a pivotal role in the diagnosis and management of cardiovascular diseases since it is real-time, cost-effective, and non-invasive. The development of artificial intelligence (AI) techniques have led to more intelligent and automatic computer-aided diagnosis (CAD) systems in echocardiography over the past few years. Automatic CAD mainly includes classification, detection of anatomical structures, tissue segmentation, and disease diagnosis, which are mainly completed by machine learning techniques and the recent developed deep learning techniques. OBJECTIVE This review aims to provide a guide for researchers and clinicians on relevant aspects of AI, machine learning, and deep learning. In addition, we review the recent applications of these methods in echocardiography and identify how echocardiography could incorporate AI in the future. METHODS This paper first summarizes the overview of machine learning and deep learning. Second, it reviews current use of AI in echocardiography by searching literature in the main databases for the past 10 years and finally discusses potential limitations and challenges in the future. RESULTS AI has showed promising improvements in analysis and interpretation of echocardiography to a new stage in the fields of standard views detection, automated analysis of chamber size and function, and assessment of cardiovascular diseases. CONCLUSIONS Compared with machine learning, deep learning methods have achieved state-of-the-art performance across different applications in echocardiography. Although there are challenges such as the required large dataset, AI can provide satisfactory results by devising various strategies. We believe AI has the potential to improve accuracy of diagnosis, reduce time consumption, and decrease the load of cardiologists.

Download Full-text

ReactionCode: a new versatile format for searching, analysis, classification, transform, and encoding/decoding of reactions

10.26434/chemrxiv.12058971.v1 ◽

2020 ◽

Author(s):

Victorien Delannée ◽

Marc Nicklaus

Keyword(s):

Machine Learning ◽

Open Source ◽

Data Exchange ◽

Similarity Searching ◽

Classification Analysis ◽

The Past ◽

Machine Learning Applications ◽

Database Organization ◽

Machine Readable ◽

Condensed Graph Of Reaction

In the past two decades a lot of different formats for molecules and reactions have been created. These formats were mostly developed for the purposes of identifiers, representation, classification, analysis and data exchange. A lot of efforts have been made on molecule formats but only few for reactions where the endeavors have been made mostly by companies leading to proprietary formats. Here, we developed a new open-source format which allows to encode and decode a reaction into multi-layers machine readable code, which aggregates reactants and products into a condensed graph of reaction (CGR). This format is flexible and can be used in a context of reaction similarity searching and classification. It is also designed for database organization, machine learning applications and as a new transform reaction language.

Download Full-text

ReactionCode: Format for Reaction Searching, Analysis, Classification, Transform, and Encoding/Decoding

10.26434/chemrxiv.12058971.v3 ◽

2020 ◽

Author(s):

Victorien Delannée ◽

Marc Nicklaus

Keyword(s):

Machine Learning ◽

Open Source ◽

Data Exchange ◽

Similarity Searching ◽

Classification Analysis ◽

The Past ◽

Machine Learning Applications ◽

Database Organization ◽

Machine Readable ◽

Condensed Graph Of Reaction

In the past two decades a lot of different formats for molecules and reactions have been created. These formats were mostly developed for the purposes of identifiers, representation, classification, analysis and data exchange. A lot of efforts have been made on molecule formats but only few for reactions where the endeavors have been made mostly by companies leading to proprietary formats. Here, we developed a new open-source format which allows to encode and decode a reaction into multi-layers machine readable code, which aggregates reactants and products into a condensed graph of reaction (CGR). This format is flexible and can be used in a context of reaction similarity searching and classification. It is also designed for database organization, machine learning applications and as a new transform reaction language.

Download Full-text

Review of machine learning applications to power systems studies

Open Access Research Journal of Engineering and Technology ◽

10.53022/oarjet.2021.1.1.0101 ◽

2021 ◽

Vol 1 (1) ◽

pp. 021-031

Author(s):

Omorogiuwa Eseosa ◽

Ashiathah Ikposhi

Keyword(s):

Machine Learning ◽

Power Systems ◽

Electricity Consumption ◽

Complex Data ◽

Accurate Analysis ◽

The Future ◽

Electric Power Networks ◽

Machine Learning Applications ◽

Past Experiences ◽

Systems Studies

The complexity of electric power networks from generation, transmission and distribution stations in modern times has resulted to generation of big and more complex data that requires more technical and mathematical analysis because it deals with monitoring, supervisory control and data acquisition all in real time. This has necessitated the need for more accurate analysis and predictions in power systems studies especially under transient, uncertainty or emergency conditions without interference of humans. This is necessary so as to minimize errors with the aim targeted towards improving the overall performance and the need to use more technical but very intelligent predictive tools has become very relevant. Machine learning (ML) is a powerful tool which can be utilized to make accurate predictions about the future nature of data based on past experiences. ML algorithms operate by building a model (mathematical or pictorial) from input examples to make data driven predictions or decisions for the future. ML can be used in conjunction with big data to build effective predictive systems or to solve complex data analytic problems. Electricity generation forecasting systems that could predict the amount of power required at a rate close to the electricity consumption have been proposed in several works. This study seeks to review machine learning applications to power system studies. This paper reviewed applications of ML tools in power systems studies.

Download Full-text

ReactionCode: format for reaction searching, analysis, classification, transform, and encoding/decoding

Journal of Cheminformatics ◽

10.1186/s13321-020-00476-x ◽

2020 ◽

Vol 12 (1) ◽

Author(s):

Victorien Delannée ◽

Marc C. Nicklaus

Keyword(s):

Machine Learning ◽

Open Source ◽

Data Exchange ◽

Similarity Searching ◽

Classification Analysis ◽

The Past ◽

Machine Learning Applications ◽

Database Organization ◽

Machine Readable ◽

Condensed Graph Of Reaction

AbstractIn the past two decades a lot of different formats for molecules and reactions have been created. These formats were mostly developed for the purposes of identifiers, representation, classification, analysis and data exchange. A lot of efforts have been made on molecule formats but only few for reactions where the endeavors have been made mostly by companies leading to proprietary formats. Here, we present ReactionCode: a new open-source format that allows one to encode and decode a reaction into multi-layer machine readable code, which aggregates reactants and products into a condensed graph of reaction (CGR). This format is flexible and can be used in a context of reaction similarity searching and classification. It is also designed for database organization, machine learning applications and as a new transform reaction language.

Download Full-text

Machine Learning-Based Algorithms to Knowledge Extraction from Time Series Data: A Review

Data ◽

10.3390/data6060055 ◽

2021 ◽

Vol 6 (6) ◽

pp. 55

Author(s):

Giuseppe Ciaburro ◽

Gino Iannace

Keyword(s):

Machine Learning ◽

Time Series ◽

Time Series Data ◽

Time Sequence ◽

Series Data ◽

Time Intervals ◽

The Past ◽

Future Behavior ◽

Measurable Variable ◽

The Future

To predict the future behavior of a system, we can exploit the information collected in the past, trying to identify recurring structures in what happened to predict what could happen, if the same structures repeat themselves in the future as well. A time series represents a time sequence of numerical values observed in the past at a measurable variable. The values are sampled at equidistant time intervals, according to an appropriate granular frequency, such as the day, week, or month, and measured according to physical units of measurement. In machine learning-based algorithms, the information underlying the knowledge is extracted from the data themselves, which are explored and analyzed in search of recurring patterns or to discover hidden causal associations or relationships. The prediction model extracts knowledge through an inductive process: the input is the data and, possibly, a first example of the expected output, the machine will then learn the algorithm to follow to obtain the same result. This paper reviews the most recent work that has used machine learning-based techniques to extract knowledge from time series data.

Download Full-text